Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 78 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.1095. Min Act: -0.1700

Data Index: 3433508 (Open Web Text)

Max Activating Token Index: 207

Text #1

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.0310. Min Act: -0.1700

Data Index: 4796446 (Open Web Text)

Max Activating Token Index: 705

Text #2

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.0620. Min Act: -0.1700

Data Index: 3377227 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9570. Min Act: -0.1700

Data Index: 772229 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9644. Min Act: -0.1700

Data Index: 8298754 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.9332. Min Act: -0.1700

Data Index: 5109090 (Open Web Text)

Max Activating Token Index: 976

Text #6

Max Range: 4.1095. Min Range: -4.1095

Max Act: 4.0027. Min Act: -0.1700

Data Index: 5156852 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8619. Min Act: -0.1700

Data Index: 8704445 (Open Web Text)

Max Activating Token Index: 899

Text #8

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8410. Min Act: -0.1700

Data Index: 6437159 (Open Web Text)

Max Activating Token Index: 684

Text #9

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8145. Min Act: -0.1700

Data Index: 4900754 (Open Web Text)

Max Activating Token Index: 593

Text #10

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8772. Min Act: -0.1700

Data Index: 4800415 (Open Web Text)

Max Activating Token Index: 906

Text #11

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.7778. Min Act: -0.1700

Data Index: 118148 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8399. Min Act: -0.1700

Data Index: 4796442 (Open Web Text)

Max Activating Token Index: 715

Text #13

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8714. Min Act: -0.1700

Data Index: 6593725 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.6507. Min Act: -0.1700

Data Index: 5267717 (Open Web Text)

Max Activating Token Index: 736

Text #15

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8136. Min Act: -0.1700

Data Index: 5388213 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.7578. Min Act: -0.1700

Data Index: 8450185 (Open Web Text)

Max Activating Token Index: 299

Text #17

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.7928. Min Act: -0.1700

Data Index: 8485676 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.7928. Min Act: -0.1700

Data Index: 1355945 (Open Web Text)

Max Activating Token Index: 969

Text #19

Max Range: 4.1095. Min Range: -4.1095

Max Act: 3.8188. Min Act: -0.1700

Data Index: 2286845 (Open Web Text)

Max Activating Token Index: 917